Legal claims defining the scope of protection, as filed with the USPTO.
1. An image processing method, applied to a local client, the method comprising: recognizing a feature of a real object from image data, the image data describing an environment of the local client that includes the real object or an environment of a peer client that includes the real object; querying a server providing services to a social network by using the feature of the real object; determining that the real object corresponds to a social network account of a registered user in the social network; obtaining an augmented reality (AR) model adaptive to the real object based on the social network account of the registered user in the social network; rendering a virtual object in the AR model according to a position of the real object in the image data, to jointly display the real object and the virtual object.
2. The method according to claim 1 , wherein the recognizing a feature of a real object from obtained image data comprises at least one of: receiving, from the peer client in the social network, the image data generated by capturing the environment of the peer client, and recognizing the feature of the real object located in the environment of the peer client from the received image data; or capturing the environment of the local client to generate the image data, and recognizing the feature of the real object located in the environment of the local client from the captured image data.
3. The method according to claim 2 , wherein the recognizing the feature of the real object located in the environment of the local client from the captured image data comprises: capturing, when communicating with the peer client in the social network, the environment of the local client to generate the image data to be transmitted to the peer client, and recognizing the feature of the real object in the environment of the local client from the captured image data; or, capturing the environment of the local client to generate the image data in response to a capturing operation of the local client, and recognizing the feature of the real object in the environment of the local client from the captured image data.
4. The method according to claim 1 , further comprising: before obtaining the AR model adaptive to the real object in the social network, determining that the recognized feature of the real object meets a condition of being recognizable in the social network, wherein the condition comprises at least one of: when image feature points are recognized, a quantity of the recognized image feature points exceeds a feature point quantity threshold; or when a biological feature is recognized, a completeness of the recognized biological feature exceeds a completeness threshold.
5. The method according to claim 1 , further comprising: querying a feature database of the social network by using the feature of the real object; determining, when the feature of the real object matches a feature of the registered user of the social network, that the real object has a registered user attribute in the social network; and determining, when the feature of the real object matches a feature of a shared object of the social network, that the real object has a shared object attribute in the social network.
6. The method according to claim 1 , wherein the obtaining an AR model adaptive to the real object comprises: obtaining, when the real object is the registered user in the social network, a preset virtual object of the registered user in the social network, wherein the virtual object comprises at least one of: a virtual item, a virtual background, or a filter; and obtaining, when the real object corresponds to a shared object of the social network, a virtual object for the shared object in the social network, wherein the virtual object comprises at least one: an article for the shared object in the social network; or an advertisement for the shared object in the social network.
7. The method according to claim 1 , wherein the recognizing a feature of a real object from obtained image data comprises: invoking a recognition service of the server, and recognizing the feature of the real object from the obtained image data; or starting an image recognition thread, and recognizing the obtained image data in the started image recognition thread, to obtain the feature of the real object in the environment.
8. The method according to claim 1 , wherein the rendering a virtual object in the AR model according to a position of the real object in the first image comprises: detecting a pose change of the real object in the image data; rendering and outputting, at the position of the real object in the first image, the virtual object adaptive to the pose change.
9. The method according to claim 1 , wherein the obtaining an AR model adaptive to the real object comprises: querying a local client for the AR model adaptive to the real object; and finding the AR model adaptive to the real object from the social network if the query at the local client fails.
10. The method according to claim 1 , wherein a face recognition server and a social decoration server are disposed in the social network, and the method further comprises: uploading the feature of the real object to the face recognition server, wherein the face recognition server is configured to retrieve the social network account of the registered user according to the feature of the real object, wherein the social decoration server is configured to receive from the face recognition server a request of pulling the AR model according to the social network account of the registered user, and wherein the face recognition server is further configured to receive from the social decoration server the AR model; and receiving from the face recognition server the AR model.
11. An image processing apparatus, comprising: a memory, configured to store an executable program, and a processor, configured to implement, when executing the executable program stored in the memory, the following operations: recognizing a feature of a real object from image data, the image data describing an environment of the local client that includes the real object or an environment of a peer client that includes the real object; querying a server providing services to a social network by using the feature of the real object; determining that the real object corresponds to a social network account of a registered user in the social network; obtaining an augmented reality (AR) model adaptive to the real object based on the social network account of the registered user in the social network; and rendering a virtual object in the AR model according to a position of the real object in the image data, to jointly display the real object and the virtual object.
12. The apparatus according to claim 11 , wherein the processor is further configured to execute the executable program to implement at least one of: receiving, from the peer client in the social network, the image data generated by capturing the environment of the peer client, and recognizing the feature of the real object located in the environment of the peer client from the received image data; or capturing the environment of the local client to generate the image data, and recognizing the feature of the real object located in the environment of the local client from the captured image data.
13. The apparatus according to claim 12 , wherein the processor is further configured to execute the executable program to implement the following operation: capturing, when communicating with the peer client in the social network, the environment of the local client to generate the image data to be transmitted to the peer client, and recognizing the feature of the real object in the environment of the local client from the captured image data; or, capturing the environment of the local client to generate the image data in response to a capturing operation of the local client, and recognizing the feature of the real object in the environment of the local client from the captured image data.
14. The apparatus according to claim 11 , wherein the processor is further configured to execute the executable program to implement: before obtaining the AR model adaptive to the real object in the social network, determining that the recognized feature of the real object meets a condition of being recognizable in the social network, wherein the condition comprises at least one of: when image feature points are recognized, a quantity of the recognized image feature points exceeds a feature point quantity threshold; or when a biological feature is recognized, a completeness of the recognized biological feature exceeds a completeness threshold.
15. The apparatus according to claim 11 , wherein the processor is further configured to execute the executable program to implement: querying a feature database of the social network by using the feature of the real object; determining, when the feature of the real object matches a feature of the registered user of the social network, that the real object has a registered user attribute in the social network; and determining, when the feature of the real object matches a feature of a shared object of the social network, that the real object has a shared object attribute in the social network.
16. The apparatus according to claim 11 , wherein the processor is further configured to execute the executable program to implement: obtaining, when the real object is the registered user in the social network, a preset virtual object of the registered user in the social network, wherein the virtual object comprises at least one of: a virtual item, a virtual background, or a filter; and obtaining, when the real object corresponds to a shared object of the social network, a virtual object for the shared object in the social network, wherein the virtual object comprises at least one: an article for the shared object in the social network; or an advertisement for the shared object in the social network.
17. The apparatus according to claim 11 , wherein the processor is further configured to execute the executable program to implement: invoking a recognition service of the server, and recognizing the feature of the real object from the obtained image data; or starting an image recognition thread, and recognizing the obtained image data in the started image recognition thread, to obtain the feature of the real object in the environment.
18. The apparatus according to claim 11 , wherein the processor is further configured to execute the executable program to implement: detecting a pose change of the real object in the image data; rendering and outputting, at the position of the real object in the first image, the virtual object adaptive to the pose change.
19. The apparatus according to claim 11 , wherein the processor is further configured to execute the executable program to implement: querying a local client for the AR model adaptive to the real object; and finding the AR model adaptive to the real object from the social network if the query at the local client fails.
20. A non-transitory storage medium, storing an executable program, the executable program, when executed by a processor, causes the processor to perform: recognizing a feature of a real object from image data, the image data describing an environment of the local client that includes the real object or an environment of a peer client that includes the real object; querying a server providing services to a social network by using the feature of the real object; determining that the real object corresponds to a social network account of a registered user in the social network; obtaining an augmented reality (AR) model adaptive to the real object based on the social network account of the registered user in the social network; rendering a virtual object in the AR model according to a position of the real object in the image data, to jointly display the real object and the virtual object.
Unknown
November 23, 2021
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.